Highway vehicle speed prediction model training method based on toll station flow

Abstract

The invention discloses a highway vehicle speed prediction model training method based on a toll station flow. In and out flows of large and small vehicles between different toll stations are taken asa characteristic, then a distance weight is added, and finally an LVQ algorithm is used for matching optimization so that time and space factors can be comprehensively considered, and a prediction speed can also be accelerated. According to the model training method, speeds of the large and small vehicles can be monitored without complex and expensive detection instruments; and the speeds of thelarge and small vehicles can be predicted only by counting station charge data, an overall traffic flow is roughly judged, speed limiting or flow limiting can be indicated for a certain section of highway through a traffic sign, an effect of controlling an overall traffic road condition is achieved, and traffic accidents can be effectively reduced.

Description

technical field [0001] The invention belongs to the technical field of data analysis, and in particular relates to a training method for expressway vehicle speed prediction models based on toll station traffic. Background technique [0002] Expressway is a symbol of modernization and a manifestation of a country's comprehensive national strength. Its construction and operation involve all aspects of the country's economic and social life. The rapid development of the automobile industry and the advancement of urbanization have brought development opportunities to expressway companies; in railway transportation Expressways play an important role in transportation in areas where capacity is tight and access channels are not smooth. With the rapid improvement of people's living standards, the number of people who own cars is increasing, but it also brings the problem of rapid increase in traffic flow on expressways. [0003] With the increase of highway mileage, traffic manage...

AI Technical Summary

Problems solved by technology

[0006] However, whether it is the first or the second type, the calculation process is often too cumbersome and the data is difficult to obtain, especially the neural network model that requires a large amount of data, and requires many parameter variables, such as considering weather, emergencies, roads, etc. The impact of many random factors such as conditions on vehicle speed

In the actual process, due to the high cost of obtaining these parameters and often missing many values, the requirements for the actual application scenarios of these methods are too high, and it is difficult to implement; if the model lacks many parameters, the final calculation results will also be different from The actual situation is quite different

Images